© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7430
    Prev
    Next
    INDEX
    Explanations

    code prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the specific token “f_,” i.e. occurrences of the letter f immediately followed by an underscore.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -2.23
    ↵↵
    -2.08
    {
    -1.87
    _
    -1.85
    [
    -1.75
     bolsillos
    -1.66
     bedrag
    -1.57
     :
    -1.56
     tremendous
    -1.56
    ,
    -1.55
    POSITIVE LOGITS
    }");
    1.80
     ของ
    1.77
     fué
    1.75
    チール
    1.72
     Of
    1.66
    Scopri
    1.65
    錞
    1.63
     to
    1.63
    besondere
    1.61
    Ingredienti
    1.61
    Activations Density 0.000%

    No Known Activations